ss-plan

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). SKILL.md instructs the runtime to read an input that can be a “link to a requirement or proposal document” (public URL) and to fetch/read it as Markdown/text, which would be outsider-authored free text injected into the agent’s LLM context via the document-reading tool.